Similar target replacement for remote sensing object detection data augmentation
Image Processing|更新时间:2024-06-27
|
Similar target replacement for remote sensing object detection data augmentation
“In the field of remote sensing image object detection, experts have proposed an augmented method based on similar object replacement, which effectively improves the model's generalization ability and detection accuracy through steps such as sample library establishment, similar class division, minority sample compensation, and replacement sample preprocessing.”
Chinese Journal of Liquid Crystals and DisplaysVol. 39, Issue 6, Pages: 813-821(2024)
作者机构:
1.中国科学院 长春光学精密机械与物理研究所, 吉林 长春 130033
2.中国科学院大学, 北京 100049
作者简介:
基金信息:
Key Research and Development Projects of Jilin Provincial Department of Science and Technology(20210201137GX)
SUN Deyao, ZHU Ming, WANG Jiarong. Similar target replacement for remote sensing object detection data augmentation[J]. Chinese journal of liquid crystals and displays, 2024, 39(6): 813-821.
DOI:
SUN Deyao, ZHU Ming, WANG Jiarong. Similar target replacement for remote sensing object detection data augmentation[J]. Chinese journal of liquid crystals and displays, 2024, 39(6): 813-821. DOI: 10.37188/CJLCD.2023-0195.
Similar target replacement for remote sensing object detection data augmentation